Comprehensive modelling of rotary desiccant wheel with different multiple regression and machine learning methods for balanced flow

Yunus Emre Güzelel, Umutcan Olmuş, Kamil Neyfel Çerçi, Orhan Büyükalaca*

*Corresponding author for this work

Research output: Contribution to journalArticleScientificpeer-review

15 Citations (Scopus)

Abstract

In this paper, several alternative models were developed with multiple linear regression and machine learning algorithms to determine the output states of silica gel desiccant wheels for balanced flow. The decision tree method was used for this purpose for the first time in open literature. All the models developed include six input parameters and a wider range than those available in the literature. Predictions from the models were compared with the master dataset used to derive the models, each of the five sub-datasets that make up the master dataset and with data available in the literature. It was determined that the most suitable models are those coded as multiple linear regression-IV (MLR-IV), multilayer perceptron regressor-III (MLPR-III) and decision tree-VII (DT-VII), and DT-VII is the best among them. The determination coefficient and root mean square error for temperature were found to be 0.9894 and 0.8743 °C for MLR-IV, 0.9817 and 1.1526 °C for MLPR-III, 0.9986 and 0.3295 °C for DT-VII, respectively. The corresponding values for humidity ratio were 0.9912 and 0.3701 g kg−1 for MLR-IV, 0.9885 and 0.4227 g kg−1 for MLPR-III, 0.9994 and 0.0995 g kg−1 for DT-VII, respectively. The results obtained revealed that the proposed models can be used safely in preliminary design, simulation and dynamic energy analysis of systems with desiccant wheels.

Original languageEnglish
Article number117544
JournalApplied Thermal Engineering
Volume199
DOIs
Publication statusPublished - 2021
Externally publishedYes

Keywords

  • Decision Tree
  • Desiccant wheel
  • Modelling
  • Multilayer Perceptron
  • Multiple linear regression

Fingerprint

Dive into the research topics of 'Comprehensive modelling of rotary desiccant wheel with different multiple regression and machine learning methods for balanced flow'. Together they form a unique fingerprint.

Cite this